Skip to content

Update Dockerfile to build for Blackwell #18095

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 9 commits into from
May 17, 2025
Merged

Update Dockerfile to build for Blackwell #18095

Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
4ea258a
Update FlashInfer
mgoin May 13, 2025
114a0f3
Add blackwell cuda arch
mgoin May 13, 2025
c044a06
Try dropping 8.6 and 12.0
mgoin May 14, 2025
cb1dc18
Merge branch 'main' into enable-flashinfer-blackwell
mgoin May 15, 2025
eabdfbb
Update flashinfer to latest
mgoin May 15, 2025
6e7eca2
Add SM 12.0
mgoin May 16, 2025
23d6c02
Revert SM 12.0
mgoin May 16, 2025
9f8ecfb
Merge branch 'main' into enable-flashinfer-blackwell
mgoin May 16, 2025
813b9a2
Merge branch 'main' into enable-flashinfer-blackwell
mgoin May 16, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions docker/Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,7 +77,7 @@ RUN --mount=type=cache,target=/root/.cache/uv \
# can be useful for both `dev` and `test`
# explicitly set the list to avoid issues with torch 2.2
# see https://github.com/pytorch/pytorch/pull/123243
ARG torch_cuda_arch_list='7.0 7.5 8.0 8.6 8.9 9.0+PTX'
ARG torch_cuda_arch_list='7.0 7.5 8.0 8.9 9.0 10.0+PTX'
ENV TORCH_CUDA_ARCH_LIST=${torch_cuda_arch_list}
# Override the arch list for flash-attn to reduce the binary size
ARG vllm_fa_cmake_gpu_arches='80-real;90-real'
Expand Down Expand Up @@ -257,8 +257,8 @@ RUN --mount=type=cache,target=/root/.cache/uv \
if [ "$TARGETPLATFORM" != "linux/arm64" ]; then \
# uv pip install --system https://github.com/flashinfer-ai/flashinfer/releases/download/v0.2.4/flashinfer_python-0.2.4+cu124torch2.6-cp38-abi3-linux_x86_64.whl ; \
# TESTING: install FlashInfer from source to test 2.7.0 final RC
FLASHINFER_ENABLE_AOT=1 TORCH_CUDA_ARCH_LIST='7.5 8.0 8.6 8.9 9.0+PTX' \
uv pip install --system --no-build-isolation "git+https://github.com/flashinfer-ai/flashinfer@v0.2.4" ; \
FLASHINFER_ENABLE_AOT=1 TORCH_CUDA_ARCH_LIST='7.5 8.0 8.9 9.0 10.0+PTX' \
uv pip install --system --no-build-isolation "git+https://github.com/flashinfer-ai/flashinfer@e00e8cedbfcb220f328fd36aa8f529f869b01e6b" ; \
fi
COPY examples examples
COPY benchmarks benchmarks
Expand Down